# SwiftKV: An Edge-Oriented Attention Algorithm and Multi-Head Accelerator for Fast, Efficient LLM Decoding

arXiv: https://arxiv.org/abs/2601.10953 · HTML: https://mlsanity.com/paper/2601.10953/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in KV cache optimization, one of 12 directions in Efficient LLM inference and serving.
- Builds on 10 of its 19 references that are in the map.
- First posted on arXiv 16 Jan 2026.

## Placed in

- Efficient LLM inference and serving / [KV cache optimization](https://mlsanity.com/inference/kv-cache-optimization/)

## Builds on (most cited first, 10 of 10)

- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [Ring Attention with Blockwise Transformers for Near-Infinite Context](https://mlsanity.com/paper/2310.01889/) (2023)
- [Online normalizer calculation for softmax](https://mlsanity.com/paper/1805.02867/) (2018)
- [FlightLLM: Efficient Large Language Model Inference with a Complete Mapping Flow on FPGAs](https://mlsanity.com/paper/2401.03868/) (2024)
- [DFX: A Low-latency Multi-FPGA Appliance for Accelerating Transformer-based Text Generation](https://mlsanity.com/paper/2209.10797/) (2022)
- [POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference](https://mlsanity.com/paper/2410.18038/) (2024)
- [EdgeLLM: A Highly Efficient CPU-FPGA Heterogeneous Edge Accelerator for Large Language Models](https://mlsanity.com/paper/2407.21325/) (2024)
- [ITA: An Energy-Efficient Attention and Softmax Accelerator for Quantized Transformers](https://mlsanity.com/paper/2307.03493/) (2023)
- [Pushing up to the Limit of Memory Bandwidth and Capacity Utilization for Efficient LLM Decoding on Embedded FPGA](https://mlsanity.com/paper/2502.10659/) (2025)

## Abstract (arXiv)

Edge acceleration for large language models is crucial for their widespread application; however, achieving fast attention inference and efficient decoding on resource-constrained edge accelerators remains challenging. This paper presents SwiftKV Attention, a per-token pipelined, low-latency single-pass attention inference algorithm, where every (kt, vt) in the KV cache is processed exactly once in a uniform per-token pipeline without score materialization, blockwise softmax, or a second pass, thereby enabling fast execution on edge accelerators with a single hardware set and no resource-intensive parallelism. Furthermore, to address the limited support for multi-head LLM decoding in existing accelerators, we design the SwiftKV-MHA accelerator, which enables high precision attention and low precision GEMV on the same processor array, achieving fast and efficient multi-head parallel decoding. Experimental results show that, on the edge accelerator, the SwiftKV Attention algorithm achieves a 7.16* speedup over native attention and significantly outperforms other attention algorithms. SwiftKV-MHA further reduces attention latency by 13.48*; under the same settings, it improves generation speed by 17.4% and increases token efficiency by 1.98* compared with state-of-the-art works.